MiniMax confirmed that Space Bunny, the anonymous model that led usage rankings on OpenRouter and elsewhere, was an early version of M3.1 Flash, and launched it on its API on October 19. Pay-as-you-go pricing is $0.15 input, $0.60 output and $0.015 cache read per million tokens, with a 1M context, text, image and video input, and an effort setting for thinking depth. Per MiniMax, it costs one third of M3 and runs 3x faster, scoring 73.7% on DeepSWE and 62.2% on Automation-Bench; the weights went live on Hugging Face on schedule on October 23 (MiniMax Community license, MXFP8), with day-0 support from Together, Inferact (vLLM) and LightSeek TokenSpeed.
Key Takeaways
- ✓Official pay-as-you-go pricing: $0.15 input / $0.60 output / $0.015 cache read per million tokens; per token that is half of M3 ($0.30/$1.20), and MiniMax does not explain how it gets one third of the cost.
- ✓Vendor benchmarks: DeepSWE v1.1 73.7% (Opus 5: 74.0%), Automation-Bench 62.2%, BabyVision with tools 91.0%, Terminal Bench 4.0 38.1% (Opus 5: 51.8%).
- ✓1M context, text/image/video input, five effort levels from low to max, default max, thinking cannot be turned off.
- ✓Weights opened October 23 at Hugging Face MiniMaxAI/MiniMax-M3.1-Flash: ungated, MiniMax Community license (not MIT/Apache), MXFP8 quantized, native multimodal MoE with about 428B total and 23B active parameters per token, plus a DSpark speculative-decoding draft head.
- ✓Migration: M2.5 and M2.7 closed to new users on October 19 and retire on November 18; M Plan and Token Plan requests now route to M3.1 Flash automatically.
- ✓Day-0 serving: Together AI runs it fully managed, MiniMax is partnering with Inferact to contribute production-inference improvements back to vLLM, and LightSeek's TokenSpeed added day-0 support.
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Core Background & Industry Pain Points
Flash-tier models carry most of the traffic in agents and coding tools, so developers care about price, speed and long context at the same time. M3.1 Flash had been in MiniMax Code as a preview since September 27, while an anonymous model called Space Bunny climbed usage rankings on OpenRouter and other platforms. On October 19 MiniMax confirmed Space Bunny was an early M3.1 Flash and opened pay-as-you-go API access.
Architecture Highlights & Mechanism
The docs list a 1M context, text, image and video input, and an effort parameter with five levels (low, medium, high, xhigh, max), defaulting to max; thinking cannot be disabled. The preview guide describes a MoE with 428B total and about 23B active parameters, sparse attention and a native vision encoder. MiniMax says it runs 3x faster than M3.
Benchmarks & Measured Results
All vendor figures: DeepSWE v1.1 73.7% (DeepSeek-V4.1-Flash 74.2%, Opus 5 74.0%), Automation-Bench 62.2% (best in the table), BabyVision with tools 91.0%, and Terminal Bench 4.0 38.1%, well below Opus 5 at 51.8%. No independent re-test yet.
Developer Quick Start
Call model MiniMax-M3.1-Flash on platform.minimax.io at $0.15 input, $0.60 output and $0.015 cache read per million tokens, about half the per-token price of M3. If you still use M2.5 or M2.7, they are closed to new users and retire on November 18, and subscription-plan requests already route to M3.1 Flash. The weights opened on schedule on October 23: download MiniMaxAI/MiniMax-M3.1-Flash from Hugging Face (MXFP8, MiniMax Community license, so read the LICENSE before commercial use). The model card says MiniMax Sparse Attention runs throughout the model and a DSpark speculative-decoding draft head is included. For hosted use, Together AI serves it fully managed; for self-hosting, vLLM (via the Inferact partnership) and TokenSpeed have day-0 support.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.